What stable-audio-tools is
The library is described as an open-source PyTorch codebase providing training and inference code for generative audio models.
What you can do with it
- Run conditional audio generation
- Run unconditional audio generation
- Train models across multiple GPUs
- Customise models and training settings
Example uses
- Generate music with a latent diffusion model
- Denoise audio with an autoencoder
- Synthesise speech with a pretrained model
Pros & cons
✓ What we like
- Training and inference code are both provided
- Models and training settings can be customised
! What to watch out for
- Work runs through PyTorch code
- Multi-GPU training is listed as a feature
FAQ
What is included?
The material lists autoencoders, latent diffusion models and MusicGen.
Can it train on several GPUs?
Yes, multi-GPU training is listed among the features.
Last reviewed: 2026-11-15
More AI music creation tools
View all →-
A.V. Mapping Video-to-music matching tool Free tools Creator tools Audio Music generator -
ACE Studio AI vocal synthesis studio that turns MIDI and lyrics into sung tracks Free tools Creator tools Music generator Song generator Composition -
AI Hits Charts for AI-generated music Free tools Creator tools Audio Music generator -
AI Jingle Maker Branded jingles and station IDs Free tools Creator tools Voiceover Music generator Ad creative -
AI Make Song Text and lyrics to full songs Freemium tools Creator tools Music generator Text to music Song generator -
AI Music Maker Music suite plus vocal cloning Freemium tools Creator tools Music generator Song generator Music stem separation